This is the official implementation of our ICML 2024 paper "MultiMax: Sparse and Multi-Modal Attention Learning""
-
Updated
Sep 1, 2026 - Python
#
activation-function-exploration
Here are 37 public repositories matching this topic...
An Artificial Neural Network (ANN) built using PyTorch to classify images in the Fashion MNIST dataset, utilizing GPU support for improved training performance.
optimizer pytorch classification ann backpropagation loss-functions forwardpropagation activation-function-exploration
-
Updated
May 26, 2026 - Jupyter Notebook
A structured, hands-on guide to neural networks and deep learning fundamentals, covering forward propagation, activation functions, backpropagation, optimization, TensorFlow, Keras, PyTorch, and CIFAR-10 image classification.
deep-learning tensorflow optimization keras pytorch neural-networks gradient-descent keras-neural-networks cifar10 loss-functions backward-propagation forward-propagation activation-function-exploration
-
Updated
Sep 25, 2026 - Python
Open ideas. Code less. Publish more.
frequency machine-learning computer-vision deep-learning neural-network pytorch artificial-intelligence fusion yolo attention sampling sequence convolutional-neural-network normalization modular-design paper-implementation detr ultralytics yolo11 activation-function-exploration
-
Updated
Feb 2, 2026 - Python
This repository contains the official implementation of the paper: "DAPA: Distribution Aware Piecewise Activation Functions for On-Device Transformer Inference and Training" (Accepted at DAC 2026).
-
Updated
Jul 23, 2026 - Python
This repository features hands-on Jupyter Notebooks, covering everything from fundamental concepts to advanced neural network architectures.
python machine-learning deep-learning neural-networks from-scratch neural-networks-from-scratch activation-function-exploration
-
Updated
May 8, 2025 - Jupyter Notebook
By Ikansh Mahajan, 3C53, 102303754, COE'27
deep-learning mlp backpropagation-learning-algorithm optimization-algorithms mlp-regressor mlp-classifier activation-function-exploration
-
Updated
May 2, 2026 - Jupyter Notebook
NN from scatch, self-coded
-
Updated
May 30, 2024 - Python
Interactive deep learning project to predict IPL innings scores from match context such as teams, venue, batsman, bowler, runs, wickets, and overs.
-
Updated
Mar 19, 2026 - Jupyter Notebook
A mini supervised learning framework
machine-learning framework model machine-learning-algorithms optimization-algorithms loss-functions activation-function-exploration
-
Updated
Sep 17, 2026 - Python
-
Updated
Dec 28, 2025 - Jupyter Notebook
We introduce two novel hybrid activation functions: S3 (Sigmoid-Softsign) and its improved version S4 (Smoothed S3)
python science machine-learning research deep-learning neural-networks sigmoid softsign activation-function-exploration
-
Updated
Nov 4, 2025 - Python
This repository demonstrates Artificial Neural Networks (ANNs) using TensorFlow and Keras, exploring various activation functions, gradient descent techniques, and optimization algorithms through classification and regression tasks.
-
Updated
Jul 16, 2026 - Jupyter Notebook
Parametric Sigmoid Linear Unit
neural-networks activation-function ml-research activation-function-exploration learnable-activation parametric-activation silu
-
Updated
Apr 19, 2026
This is a Fake and AI image prediction using Transfer Learning
-
Updated
Apr 21, 2025 - Python
A production-ready Deep Learning project demonstrating an Artificial Neural Network (ANN) trained on the classic Iris dataset, served via a high-performance FastAPI backend with a modern, responsive animated web UI.
deep-learning neural-network models optimizer perceptron ann loss-functions dense tensorflow-keras activation-function-exploration
-
Updated
Sep 2, 2026 - Jupyter Notebook
This is a custom-built neural network that detects handwritten numbers from image inputs. It uses ReLU activation in the hidden layers and a softmax activation function in the output layer for classification. The model is trained using backpropagation with a loss function to minimize prediction errors, achieving over 99% accuracy when predicting
-
Updated
Apr 11, 2025 - Python
Neural network from scratch using cupy with experiments on a ton of things, including my own optimizer and activation function
machine-learning metrics optimization numpy mathematics cnn supervised-learning convolutional-neural-networks attention-mechanism from-scratch risk-minimization fourier-transform cupy im2col dogs-vs-cats made-from-scratch puremath activation-function-exploration mixup-augmentation custom-optimizer
-
Updated
Jun 8, 2026 - Jupyter Notebook
-
Updated
Feb 13, 2026 - Jupyter Notebook
-
Updated
Feb 18, 2026 - Jupyter Notebook
Add this topic to your repo
To associate your repository with the activation-function-exploration topic, visit your repo's landing page and select "manage topics."